scikit-bio

Biological data toolkit. Sequence analysis, alignments, phylogenetic trees, diversity metrics (alpha/beta, UniFrac), ordination (PCoA), PERMANOVA, FASTA/Newick I/O, for microbiome analysis.

Quality

65%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./backend/cli/skills/biology/scikit-bio/SKILL.md

Quality

Content

61%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, highly actionable overview of the library with correctly offloaded API reference material, weakened by duplicated overview content and workflows that lack validation checkpoints.

Suggestions

Add validation checkpoints to the Common Workflows (e.g., verify counts are integers and tree tips match OTU IDs before computing UniFrac/Faith's PD, with a fix-and-retry step on mismatch).

Trim the Overview and 'When to Use This Skill' sections, which duplicate the frontmatter description, and cut obvious 'Important notes' to reduce token load.

Make code examples self-contained by defining inputs (e.g., a small counts array and sample_ids list) or by linking to the corresponding runnable example in references/api_reference.md.

Dimension	Reasoning	Score
Conciseness	The ten capability sections are dense and free of concept-explanation padding, but the Overview and 'When to Use This Skill' sections largely duplicate the frontmatter description, and a few 'Important notes' state near-obvious facts, so the body could be meaningfully tightened.	3 / 5
Actionability	Abundant executable code using real scikit-bio APIs (e.g., alpha_diversity('shannon', counts_matrix, ids=sample_ids), permanova(distance_matrix, grouping, permutations=999)), but many snippets rely on undefined placeholders (seq1, grouping, dm1, counts_matrix) rather than being fully copy-paste ready.	4 / 5
Workflow Clarity	The four 'Common Workflows' give clear step sequences (e.g., 'Read BIOM table → Calculate alpha/beta diversity → Ordination (PCoA) → Statistical testing'), but no validation checkpoints or error-recovery guidance exist (e.g., verifying integer counts or tree-tip/OTU-ID matching before diversity calculations).	3 / 5
Progressive Disclosure	Good structure: the body is a capability overview and detailed API material is correctly split into a real, clearly signaled, one-level-deep references/api_reference.md with an enumerated contents list; however, the ~440-line body still inlines detail (e.g., Distance Matrices, Protein Embeddings) that could live in the reference, leaving minor organization gaps.	4 / 5
	Total	14 / 20 Passed

Description

70%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A specific, distinctive description with good trigger vocabulary for the microbiome/bioinformatics domain, held back mainly by the absence of an explicit 'Use when...' trigger clause and a somewhat generic opening phrase.

Suggestions

Add an explicit trigger clause, e.g., 'Use when the user works with biological sequences, microbiome or diversity data, phylogenetic trees, or mentions FASTA, Newick, BIOM, UniFrac, or PERMANOVA.'

Include common synonyms and file extensions users naturally mention (.fasta, .fastq, .nwk, .biom, OTU/ASV tables, bioinformatics) to broaden trigger coverage.

Replace the vague opener 'Biological data toolkit' with a concrete action statement such as 'Analyzes biological sequences and microbiome data.'

Dimension	Reasoning	Score
Specificity	The description lists many specific capabilities ('diversity metrics (alpha/beta, UniFrac)', 'ordination (PCoA)', 'PERMANOVA', 'FASTA/Newick I/O'), but opens with the vague 'Biological data toolkit' and uses domain noun-phrases rather than concrete action verbs, leaving minor gaps versus the comprehensive anchor.	4 / 5
Completeness	The 'what' is clear and detailed, but there is no explicit 'Use when...' clause or equivalent trigger guidance; 'for microbiome analysis' is a purpose qualifier that only weakly implies when to use the skill, which caps this at 3 per the rubric.	3 / 5
Trigger Term Quality	Strong natural terms a bioinformatics user would say ('sequence analysis', 'phylogenetic trees', 'UniFrac', 'PERMANOVA', 'microbiome analysis'), but a few common variations are missing (e.g., '.fasta' extensions, 'bioinformatics', 'BIOM', 'OTU/ASV', 'QIIME').	4 / 5
Distinctiveness Conflict Risk	Highly specific niche terms (UniFrac, PERMANOVA, PCoA, Newick, microbiome analysis) create a clear niche with distinct triggers and minimal risk of firing for an unrelated skill.	5 / 5
	Total	16 / 20 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/biology/scikit-bio/SKILL.md
Commit: 4082a2e

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.